© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14742
    Prev
    Next
    INDEX
    Explanations

    a variety of words with high sensibility seemingly having to do with general context rather than the specific word, including actions, descriptions, relation words or even numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.74
    AnimationsModule
    -0.63
    featureID
    -0.63
    DrawerToggle
    -0.59
     Senses
    -0.54
     Infórmanos
    -0.52
    usepackage
    -0.51
    SwitchCompat
    -0.51
    weiser
    -0.51
    bootstrapcdn
    -0.51
    POSITIVE LOGITS
    UnknownFields
    0.54
    DockStyle
    0.52
    الحياه
    0.50
    ViewFeatures
    0.50
     challenge
    0.47
    ್ದ
    0.46
    HtmlAttribute
    0.46
    saraba
    0.46
    layah
    0.45
    henswürdigkeiten
    0.45
    Activations Density 31.178%

    No Known Activations